| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12531328320802004, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005012531328320802, | |
| "grad_norm": 20.869874954223633, | |
| "learning_rate": 1e-05, | |
| "loss": 20.1344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005012531328320802, | |
| "eval_loss": 10.39857006072998, | |
| "eval_runtime": 28.3062, | |
| "eval_samples_per_second": 5.935, | |
| "eval_steps_per_second": 0.742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010025062656641603, | |
| "grad_norm": 20.313007354736328, | |
| "learning_rate": 2e-05, | |
| "loss": 22.4254, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015037593984962405, | |
| "grad_norm": 15.272883415222168, | |
| "learning_rate": 3e-05, | |
| "loss": 20.2144, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020050125313283207, | |
| "grad_norm": 22.251083374023438, | |
| "learning_rate": 4e-05, | |
| "loss": 22.7775, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02506265664160401, | |
| "grad_norm": 18.530513763427734, | |
| "learning_rate": 5e-05, | |
| "loss": 19.4961, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 20.28190803527832, | |
| "learning_rate": 6e-05, | |
| "loss": 21.2481, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 20.61719512939453, | |
| "learning_rate": 7e-05, | |
| "loss": 20.0061, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.040100250626566414, | |
| "grad_norm": 24.68893814086914, | |
| "learning_rate": 8e-05, | |
| "loss": 17.2958, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.045112781954887216, | |
| "grad_norm": 21.156003952026367, | |
| "learning_rate": 9e-05, | |
| "loss": 16.7236, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.045112781954887216, | |
| "eval_loss": 8.052587509155273, | |
| "eval_runtime": 28.367, | |
| "eval_samples_per_second": 5.922, | |
| "eval_steps_per_second": 0.74, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05012531328320802, | |
| "grad_norm": 22.940866470336914, | |
| "learning_rate": 0.0001, | |
| "loss": 15.396, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05513784461152882, | |
| "grad_norm": 28.320890426635742, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 17.2894, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 25.803590774536133, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 12.782, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06516290726817042, | |
| "grad_norm": 22.771900177001953, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 11.7643, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 24.09734344482422, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 8.7052, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07518796992481203, | |
| "grad_norm": 17.444034576416016, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 5.8894, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08020050125313283, | |
| "grad_norm": 20.63741111755371, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.2684, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08521303258145363, | |
| "grad_norm": 17.476707458496094, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 5.7511, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09022556390977443, | |
| "grad_norm": 12.589031219482422, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 3.3076, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09022556390977443, | |
| "eval_loss": 1.4214398860931396, | |
| "eval_runtime": 28.3828, | |
| "eval_samples_per_second": 5.919, | |
| "eval_steps_per_second": 0.74, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 12.787721633911133, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.5447, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10025062656641603, | |
| "grad_norm": 13.530546188354492, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.2347, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 15.857293128967285, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.0769, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11027568922305764, | |
| "grad_norm": 11.907310485839844, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.9489, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11528822055137844, | |
| "grad_norm": 7.293683052062988, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.6826, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 7.3750128746032715, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.6393, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12531328320802004, | |
| "grad_norm": 4.739354133605957, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5386, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.940561908563968e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |